Cite
Notes
Only stored in your browser.
Attribution
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
arXiv 2025
from 1 papers
Lu Qi
Ming-Hsuan Yang
Wenbo Zhu
Xinting Hu
Xinyu Ye
Xu Yang
Yingzhe Peng
Yizhou Zhou
Yongliang Wu